How to Use Scribe v2 in Muse
Scribe v2 turns recorded interviews, meetings, and videos into transcripts with word timestamps and speaker labels. Unlike Scribe v2 Realtime, it focuses on long, complex recordings.
Prompts to try with Scribe v2 in Muse
Copy an example into Muse, or ask in your own words.
Use Scribe v2 to transcribe this recorded interview with speaker labels and cleanup turned off. Then list five useful quotations with their timestamps.
Transcribe this podcast episode with Scribe v2. Then draft captions from the word timestamps and preserve the original language.
Use Scribe v2 on this meeting recording with filler-word cleanup enabled. Then summarize decisions and open questions, citing transcript timestamps.
Use Scribe v2 to transcribe this Spanish lecture, specifying Spanish as the spoken language. Then make a Spanish study outline with timestamped sections.
Transcribe this recorded panel discussion with Scribe v2 and speaker labels. Then summarize each speaker's position and flag overlapping passages for listening review.
How to set up Scribe v2 in Muse
Pick the way that suits you. Each takes about two minutes.
Use the Muse connector
- Create an API key
Create one under API keys in the Spiral console.
- Send Muse this message
Muse reads Spiral's skill and asks for an API key.
set up https://spiral.ai/SKILL.md
- Give Muse the key
Paste the key when Muse asks for it, never in the chat itself.
Use the Spiral skill
- Send Muse this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Scribe v2
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "elevenlabs", "model": "scribe_v2", "input": { "file": "<file>" } }'
Then paste one of the prompts above: Muse finds Scribe v2 on Spiral, shows the price and runs it.
Scribe v2 providers and prices
Spiral runs Scribe v2 through ElevenLabs. Open a card for today's price, with every fee included.
Settings you can ask for
Scribe v2 works from your file and source URL. Ask Muse for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | 0 to 2147483647 | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647. | |
| Diarize | on or off | off | Whether to annotate which speaker is currently talking in the uploaded file. |
| File format | pcm_s16le_16 or other | other | The format of input audio. Options are 'pcm_s16le_16' or 'other' For |
| No verbatim | on or off | off | If true, the transcription will not have any filler words, false starts and non-speech sounds. Only supported with scribe_v2 model. |
| Temperature | 0 to 2 | Controls the randomness of the transcription output. Accepts values between 0.0 and 2.0, where higher values result in more diverse and less deterministic results. If omitted, we will use a temperature based on the model you selected which is usually 0. | |
| Number of speakers | 1 to 32 | The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports. | |
| Tag audio events | on or off | on | Whether to tag audio events like (laughter), (footsteps), etc. in the transcription. |
| Use multi channel | on or off | off | Whether the audio file contains multiple channels where each channel contains a single speaker. When enabled, each channel is transcribed independently. By default a separate transcript is returned per channel; set multichannel_output_style='combined' to instead receive a single transcript with all channels merged and sorted by time. Each word in the response includes a 'channel_index' field indicating which channel it was spoken on. A maximum of 5 channels is supported. Each channel is billed independently at the full audio duration, so cost scales linearly with the number of channels. |
| Detect speaker roles | on or off | off | Whether to detect speaker roles (agent vs customer). Requires diarize=true. Cannot be used with use_multi_channel=true. When enabled, speaker_id values will be 'agent' and 'customer' instead of 'speaker_0', 'speaker_1', etc. Usage incurs an additional 10% surcharge on base transcription cost. |
| Diarization threshold | 0.1 to 0.4 | Diarization threshold to apply during speaker diarization. A higher value means there will be a lower chance of one speaker being diarized as two different speakers but also a higher chance of two different speakers being diarized as one speaker (less total speakers predicted). A low value means there will be a higher chance of one speaker being diarized as two different speakers but also a lower chance of two different speakers being diarized as one speaker (more total speakers predicted). Can only be set when diarize=True and num_speakers=None. Defaults to None, in which case we will choose a threshold based on the model_id (0.22 usually). | |
| Timestamps granularity | none, word, or character | word | The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word. |
| Multichannel output style | separate or combined | separate | Controls the response shape when use_multi_channel is enabled. 'separate' (default) returns one transcript per channel under 'transcripts'. 'combined' merges all channels into a single transcript whose words are sorted by start time, each carrying a 'channel_index' - matching the single-channel response shape. 'combined' requires timestamps (timestamps_granularity must not be 'none') and does not support entity detection or redaction. |
Every API field of Scribe v2 is on its tool page: open its card above.
What can you do with Scribe v2 in Muse?
Turn recorded conversations into transcripts you can question and revisit. Your chat agent can use Scribe v2 speaker labels and timestamps to prepare summaries, quotation lists, and caption drafts.
Interview transcripts for research
Use Scribe v2 to transcribe recorded interviews with speaker labels and timestamps, then have your agent organize excerpts by research question.
Podcast caption drafts
Use Scribe v2 word timestamps as the basis for captions, then have your agent group words into readable subtitle lines.
Meeting records
Create a speaker-labeled transcript with Scribe v2, then have your agent extract decisions and action items with references to the recording.
Searchable lecture archives
Transcribe recorded lectures with Scribe v2, then have your agent build a topic index linked to transcript timestamps.
Recorded call review
Use Scribe v2 to separate speakers in recorded calls, then have your agent collect timestamped examples for a reviewer to assess.
Readable dictation
Use Scribe v2 with No Verbatim mode to turn spoken drafts into text with fewer fillers and repetitions.
Multilingual content archives
Use Scribe v2 to create original-language transcripts of recordings in supported languages, then have your agent organize them for search or later translation.
Scribe v2 success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| Scribe v2 | 99.0% | 3.3s | 395 |
More on Scribe v2 and Muse
Overview
Scribe v2 in other agents
Questions about Scribe v2 in Muse
Can Muse use Scribe v2?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Scribe v2 like any built-in tool.
How much does Scribe v2 cost in Muse?
$0.26 per hour of audio, per channel. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.
Do I need an ElevenLabs account to use Scribe v2 in Muse?
You need no ElevenLabs account. Muse uses one Spiral API key for every tool, and Spiral runs Scribe v2 on its own ElevenLabs account.
How long does it take to set up Scribe v2 in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while Scribe v2 runs?
Scribe v2 runs in the background. Muse starts the run, checks on it and gives you the json when it's ready.
What is Scribe v2 best for?
Recorded interviews, meetings, podcasts, and videos that need searchable transcripts or captions. It is designed for long, complex recordings, while Scribe v2 Realtime targets live audio.
Which languages does Scribe v2 support, and does it translate?
Scribe v2 supports more than 90 languages and transcribes speech in the language spoken. Translation requires a separate step.
Can Scribe v2 separate speakers?
Scribe v2 supports speaker diarization for up to 32 speakers. Review labels where people interrupt or speak over one another.
How long can a recording be?
ElevenLabs documents up to 15 hours per recording in standard transcription mode.
Can Scribe v2 remove ums and repeated phrases?
Yes. No Verbatim mode removes filler words, repeated phrases, and stuttering; keep it off when you need to study the original wording and delivery.
Start using Scribe v2 in Muse
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse:
set up https://spiral.ai/SKILL.md


